CtrlK
BlogDocsLog inGet started
Tessl Logo

clean-code

This skill embodies the principles of "Clean Code" by Robert C. Martin (Uncle Bob). Use it to transform "code that works" into "code that is clean."

46

Quality

49%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/clean-code/SKILL.md

The canonical home for this skill is clean-code in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

53%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured but largely restatement-style summary of Clean Code principles Claude already knows, with limited executable guidance and no real workflow with validation checkpoints. Organization is its strongest aspect.

Suggestions

Trim principle restatements Claude already knows and replace them with project-specific conventions or the team's actual standards that Claude would not infer.

Add a concrete, runnable refactoring example (e.g. a before/after function split) instead of relying on one illustrative benefits snippet.

Turn the checklist into an explicit review workflow with a validation checkpoint (e.g. 'run tests after each refactor step; only proceed when green') to support batch or destructive refactors.

DimensionReasoningScore

Conciseness

The body is bullet-pointed and reasonably lean, but it restates well-known Clean Code principles (the F.I.R.S.T. test laws, Law of Demeter, the three TDD laws) that Claude already knows, fitting 'Mostly efficient but includes some unnecessary explanation or could be tightened'; not a 2 because it avoids long prose padding.

3 / 5

Actionability

There are some concrete rules ("0 is ideal, 1-2 is okay, 3+ requires justification", "smaller than 20 lines") and one illustrative code snippet, but most of the body is abstract principle statements with no executable refactoring commands or runnable examples, matching 'Some concrete guidance but incomplete'.

3 / 5

Workflow Clarity

The closing 'Implementation Checklist' provides a loose review sequence, but there is no real multi-step workflow with validation checkpoints; this is a principles reference rather than a sequenced procedure, fitting 'Steps listed but validation gaps; checkpoints missing or implicit'.

3 / 5

Progressive Disclosure

No bundle files exist and none are needed; the single SKILL.md is well-organized with clear numbered sections and a checklist, fitting 'Good structure; most content is appropriately placed'; not a 5 only because some material (detailed examples, the smell heuristics) could optionally live in a reference file.

4 / 5

Total

13

/

20

Passed

Description

45%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is clear about its philosophical lineage but vague on concrete actions and weak on explicit trigger scenarios. It reads more as a tagline than a 'what + when' specification.

Suggestions

Replace the abstract 'transform code that works into code that is clean' with concrete actions, e.g. 'Refactor functions to be smaller and single-purpose, rename variables to be intention-revealing, remove code smells'.

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when reviewing a PR, refactoring legacy code, or when the user asks to clean up, refactor, or improve code quality'.

Include common user phrasings ('refactor', 'code review', 'code smells') so the skill triggers on natural requests.

DimensionReasoningScore

Specificity

The description names the domain (Clean Code) but offers only one abstract action — "transform 'code that works' into 'code that is clean'" — with no concrete refactoring operations, matching the 'Names the domain but actions are minimal or generic' anchor; it is not a 3 because no specific concrete actions are enumerated.

2 / 5

Completeness

The 'what' is reasonably clear (apply Clean Code principles to clean up code), but the trigger guidance is "Use it to transform..." which restates the action rather than naming a scenario; per the rubric a missing explicit 'Use when...' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Recognizable terms like "Clean Code", "Robert C. Martin (Uncle Bob)", and "code that is clean" are present, but natural request phrasings users actually say ("refactor", "code review", "code smells", "clean up this code") are missing, fitting the 'Some relevant keywords but missing common variations or synonyms' anchor.

3 / 5

Distinctiveness Conflict Risk

The explicit book attribution gives it a recognizable niche, but the broad framing of turning working code into clean code overlaps noticeably with general refactoring, code-review, and linting skills, matching 'Somewhat specific but could still overlap with similar skills'.

3 / 5

Total

11

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.